TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization

Open paper
Benchmark Model Rank Results
audio-generation-on-audiocapsTangoFlux#3FD_openl3: 75.1KL_passt: 1.15IS: 12.2CLAP_LAION: 0.488
audio-generation-on-audiocapsTangoFlux-base#5FD_openl3: 79.7KL_passt: 1.23IS: 10.7CLAP_LAION: 0.438

Rank counts only results with a code link.